© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 21782
    Prev
    Next
    INDEX
    Explanations

    memories or recollections

    oai_token-act-pair · gpt-3.5-turbo

    references to memories and recollections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olitical
    -0.83
    blogspot
    -0.82
    arent
    -0.81
    orem
    -0.81
    yright
    -0.78
    sonian
    -0.74
    redit
    -0.72
    vernment
    -0.72
    ahime
    -0.72
    acies
    -0.71
    POSITIVE LOGITS
     vividly
    1.58
     seeing
    1.32
     encountering
    1.28
     hearing
    1.27
     waking
    1.25
     remembering
    1.15
     fond
    1.11
     thinking
    1.10
     witnessing
    1.10
     recalling
    1.09
    Activations Density 0.082%

    No Known Activations